Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    checkmark

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     toggle
    0.43
    testing
    0.41
     StringIO
    0.40
     Fli
    0.40
     testing
    0.39
     Belvedere
    0.38
     Chas
    0.37
     dialog
    0.37
     Jonas
    0.37
     oscillate
    0.37
    POSITIVE LOGITS
    ✔
    1.47
     ✔
    1.46
    ✓
    1.45
     ✓
    1.39
     ✅
    1.37
    checkmark
    1.28
    ✔️
    1.28
    ✅
    1.27
     √
    1.23
    1.22
    Act Density 0.009%

    No Known Activations